adaamko commited on
Commit
52dc2fd
·
verified ·
1 Parent(s): b21681a

Upload model files

Browse files
Files changed (3) hide show
  1. README.md +3 -0
  2. config.json +46 -3
  3. model.safetensors +2 -2
README.md CHANGED
@@ -1,3 +1,6 @@
 
 
 
1
  # chiliground-base-modernbert-v1
2
 
3
  A sentence classification model for extracting relevant spans from documents based on a question.
 
1
+ ---
2
+ {}
3
+ ---
4
  # chiliground-base-modernbert-v1
5
 
6
  A sentence classification model for extracting relevant spans from documents based on a question.
config.json CHANGED
@@ -1,5 +1,48 @@
1
  {
2
- "model_name": "answerdotai/ModernBERT-base",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "hidden_dim": 768,
4
- "num_labels": 2
5
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "QAModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
  "hidden_dim": 768,
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_name": "answerdotai/ModernBERT-base",
33
+ "model_type": "modernbert",
34
+ "norm_bias": false,
35
+ "norm_eps": 1e-05,
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 22,
38
+ "pad_token_id": 50283,
39
+ "position_embedding_type": "absolute",
40
+ "reference_compile": null,
41
+ "repad_logits_with_grad": false,
42
+ "sep_token_id": 50282,
43
+ "sparse_pred_ignore_index": -100,
44
+ "sparse_prediction": false,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.50.3",
47
+ "vocab_size": 50368
48
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcfe8b9149d531884604687d64208f1a77bf81d09b91f327fd2d48b73555a2cd
3
- size 596077104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdab54d33c0e055274ce8c9bac899a7e00a98814710c5fad4b768c20330b1c27
3
+ size 596077128